Tiffany Michelle Barnes

North Carolina State University | NCSU · Department of Computer Science

Factual knowledge and procedural knowledge are knowing ‘That’ and ‘How,’ respectively, whereas conditional knowledge is the metacognitive knowledge of ‘When’ and ‘Why.’ As prior work has found that students with conditional knowledge spontaneously transferred such knowledge across intelligent tutoring systems, this work assesses the impact of metac...

Black women remain severely underrepresented in computing despite ongoing efforts to diversify the field. Given that Black women exist at the intersection of both racial and gendered identities, tailored approaches are necessary to address the unique barriers Black women face in computing. However, it is difficult to quantitatively evaluate the eff...

We explore eXplainable AI (XAI) to enhance user experience and understand the value of explanations in AI-driven pedagogical decisions within an Intelligent Pedagogical Agent (IPA). Our real-time and personalized explanations cater to students’ attitudes to promote learning. In our empirical study, we evaluate the effectiveness of personalized expl...

We explore eXplainable AI (XAI) to enhance user experience and understand the value of explanations in AI-driven pedagogical decisions within an Intelligent Pedagogical Agent (IPA). Our real-time and personalized explanations cater to students’ attitudes to promote learning. In our empirical study, we evaluate the effectiveness of personalized expl...

We provide insights on log data that inspired our definition of early versus late switch on the logic tutor. Recall that logic training has five levels with an incremental linear degree of difficulty, each consisting of four problems. Each problem can be solved by either following the default Forward-Chaining (FC) strategy or by switching to the Ba...

Two metacognitive knowledge types in deductive domains are procedural and conditional. This work presents a preliminary study on the impact of metacognitive knowledge and motivation on transfer across two Intelligent Tutoring Systems (ITSs), then two experiments on metacognitive knowledge instruction. Throughout this work, we trained students on a...

Learning to derive subgoals reduces the gap between experts and students and makes students prepared for future problem solving. Researchers have explored subgoal-labeled instructional materials in traditional problem solving and within tutoring systems to help novices learn to subgoal. However, only a little research is found on problem-solving st...

Deep Reinforcement Learning (Deep RL) has revolutionized the field of Intelligent Tutoring Systems by providing effective pedagogical policies. However, the "black box" nature of Deep RL models makes it challenging to understand these policies. This study tackles this challenge by applying fuzzy logic to distill knowledge from Deep RL-induced polic...

In deductive domains, three metacognitive knowledge types in ascending order are declarative, procedural, and conditional learning. This work leverages Deep Reinforcement Learning (DRL) in providing adaptive metacognitive interventions to bridge the gap between the three knowledge types and prepare students for future learning across Intelligent Tu...

This work compares two approaches to provide metacognitive interventions and their impact on preparing students for future learning across Intelligent Tutoring Systems (ITSs). In two consecutive semesters, we conducted two classroom experiments: Exp. 1 used a classic artificial intelligence approach to classify students into different metacognitive...

Providing timely assistance to students in intelligent tutoring systems is a challenging research problem. In this study, we aim to address this problem by determining when to provide proactive help with autoencoder based feature learning and a deep reinforcement learning (DRL) model. To increase generalizability, we only use domain-independent fea...

Intelligent Tutoring Systems (ITSs) leverage AI to adapt to individual students, and employ pedagogical policies to decide what instructional action to take next. A number of researchers applied Reinforcement Learning (RL) and Deep RL (DRL) to induce effective pedagogical policies. Most prior work, however, has been developed independently for a sp...

This work compares two approaches to provide metacognitive interventions and their impact on preparing students for future learning across Intelligent Tutoring Systems (ITSs). In two consecutive semesters, we conducted two classroom experiments: Exp. 1 used a classic artificial intelligence approach to classify students into different metacognitive...

Humans adopt various problem-solving strategies depending on their mastery level, problem type, and complexity. Many of these problem-solving strategies have been integrated within intelligent problem-solvers to solve structured and complex problems efficiently. One such strategy is the means-ends analysis which involves comparing the goal and the...

The assistance dilemma is a well-recognized challenge to determine when and how to provide help during problem solving in intelligent tutoring systems. This dilemma is particularly challenging to address in domains such as logic proofs, where problems can be solved in a variety of ways. In this study, we investigate two data-driven techniques to ad...

Self-organizing neuro-fuzzy Q-networks leverage hybrid learning to produce effective and interpretable policies, which aids human-in-the-loop for design or explainability.

A self-organizing neuro-fuzzy Q-network is proposed and presented, capable of performing offline fuzzy reinforcement learning in high-dimensional spaces using model-free algorithms.

In this paper, we propose a systematic design process for automatically generating self-organizing neuro-fuzzy Q-networks by leveraging unsupervised learning and an offline, model-free fuzzy reinforcement learning algorithm called Fuzzy Conservative Q-learning (FCQL). Our FCQL offers more effective and interpretable policies than deep neural networ...

Deep Reinforcement Learning (Deep RL) has revolutionized the field of Intelligent Tutoring Systems by providing effective pedagogical policies. However, the "black box" nature of Deep RL models makes it challenging to understand these policies. This study tackles this challenge by applying fuzzy logic to distill knowledge from Deep RL-induced polic...

In deductive domains, three metacognitive knowledge types in ascending order are declarative, procedural, and conditional learning. This work leverages Deep Reinforcement Learning (DRL) in providing adaptive metacognitive interventions to bridge the gap between the three knowledge types and prepare students for future learning across Intelligent Tu...

This work compares two approaches to provide metacognitive interventions and their impact on preparing students for future learning across Intelligent Tutoring Systems (ITSs). In two consecutive semesters, we conducted two classroom experiments: Exp. 1 used a classic artificial intelligence approach to classify students into different metacognitive...

Metacognitive skills have been commonly associated with preparation for future learning in deductive domains. Many researchers have regarded strategy- and time-awareness as two metacognitive skills that address how and when to use a problem-solving strategy, respectively. It was shown that students who are both strategy-and time-aware (StrTime) out...

In this work, we investigate how two factors, metacognitive skills and motivation, would impact student learning across domains. More specifically, our primary goal is to identify the critical, yet robust, interaction patterns of these two factors that would contribute to students' performance in learning logic first and then their performance on a...

One fundamental goal of learning is preparation for future learning (PFL) and being able to extend acquired skills and problem-solving strategies to different domains and environments. While substantial research has shown that PFL can be accelerated by obtaining metacognitive skills or influenced by the individual's motivation, no prior work invest...

While Reinforcement learning (RL), especially Deep RL (DRL), has shown outstanding performance in video games, little evidence has shown that DRL can be successfully applied to human-centric tasks where the ultimate RL goal is to make the human-agent interactions productive and fruitful. In real-life, complex, human-centric tasks, such as education...

Many block-based programming environments have proven to be effective at engaging novices in learning programming. However, most offer only restricted access to the outside world, limiting learners to commands and computing resources built in to the environment. Some allow learners to drag and drop files, connect to sensors and robots locally or is...

Regardless of skill level and background, programming can be challenging for all students. However, in the early stages of learning, challenges may particularly lead to a decrease in students’ sense of self-efficacy and interest in computer science. Hence, finding the moments when novices struggle during programming will help us provide support and...

Research on intelligent tutoring systems has been exploring data-driven methods to deliver effective adaptive assistance. While much work has been done to provide adaptive assistance when students seek help, they may not seek help optimally. This had led to the growing interest in proactive adaptive assistance, where the tutor provides unsolicited...

Metacognitive skills have been commonly associated with preparation for future learning in deductive domains. Many researchers have regarded strategy- and time-awareness as two metacognitive skills that address how and when to use a problem-solving strategy, respectively. It was shown that students who are both strategy-and time-aware (StrTime) out...

Positive student self-efficacy has been linked to undergraduate computer science students' improved retention rates and success in the major, with self-efficacy in programming being particularly important. To improve poor self-efficacy in programming, especially for novices, we must understand the moments that affect students' self-perceived progra...

Learning to derive subgoals reduces the gap between experts and students and makes students prepared for future problem solving. Researchers have explored subgoal labeled instructional materials with explanations in traditional problem solving and within tutoring systems to help novices learn to subgoal. However, only a little research is found on...

Data-driven programming feedback systems can help novices to program in the absence of a human tutor. Prior evaluations showed that these systems improve learning in terms of test scores, or task completion efficiency. However, crucial aspects which can impact learning or reveal insights important for future improvement of such systems are ignored...

Metacognitive skills have been commonly associated with preparation for future learning in deductive domains. Many researchers have regarded strategy- and time-awareness as two metacognitive skills that address how and when to use a problem-solving strategy, respectively. It was shown that students who are both strategy-and time-aware (StrTime) out...

Research on intelligent tutoring systems has been exploring data-driven methods to deliver effective adaptive assistance. While much work has been done to provide adaptive assistance when students seek help, they may not seek help optimally. This had led to the growing interest in proactive adaptive assistance, where the tutor provides unsolicited...

In computer science education timely help seeking during large programming projects is essential for student success. Help-seeking in typical courses happens in office hours and through online forums. In this research, we analyze students coding activities and help requests to understand the interaction between these activities. We collected studen...

Historically, female students have shown low interest in the field of computer science. Previous computer science curricula have failed to address the lack of female-centered computer science activities, such as socially relevant and real-life applications. Our new summer camp curriculum introduces the topics of artificial intelligence (AI), machin...

Student modeling sits at the epicenter of adaptive learning technology. In contrast to the voluminous work on student modeling for well-defined domains such as algebra, there has been little research on student modeling in programming (SMP) due to data scarcity caused by the unbounded solution spaces of open-ended programming exercises. In this wor...

Deductive domains are typical of many cognitive skills in that no single problem-solving strategy is always optimal for solving all problems. It was shown that students who know how and when to use each strategy (StrTime) outperformed those who know neither and stick to the default strategy (Default). In this work, students were trained on a logic...

Knowledge tracing (KT) models are a popular approach for predicting students' future performance at practice problems using their prior attempts. Though many innovations have been made in KT, most models including the state-of-the-art Deep KT (DKT) mainly leverage each student's response either as correct or incorrect, ignoring its content. In this...

Theories on learning show that formative feedback that is immediate, specific, corrective, and positive is essential to improve novice students’ motivation and learning. However, most prior work on programming feedback focuses on highlighting student's mistakes, or detecting failed test cases after they submit a solution. In this article, we presen...

The COVID-19 pandemic led to an urgent need for professional development (PD) experiences to support teacher learning across hybrid and digital contexts. This study investigates teachers' experiences in a Virtual Pivot, a PD workshop designed to support computational thinking integration into disciplinary teaching. Participants were 151 middle and...

One fundamental goal of learning is preparation for future learning (PFL) and being able to extend acquired skills and problem-solving strategies to different domains and environments. While substantial research has shown that PFL can be accelerated by obtaining metacognitive skills or influenced by the individual's motivation, no prior work invest...

Classroom dashboards are designed to help instructors effectively orchestrate classrooms by providing summary statistics, activity tracking, and other information. Existing dashboards are generally specific to an LMS or platform and they generally summarize individual work, not group behaviors. However, CS courses typically involve constellations o...